Statistical machine translation systems are usually trained on large amounts of bilingual text (used to learn a translation model), and also large amounts of monolingual text in th...
In Minimum Error Rate Training (MERT), BLEU is often used as the error function, despite the fact that it has been shown to have a lower correlation with human judgment than other...
Recent advances in statistical machine translation have used approximate beam search for NP-complete inference within probabilistic translation models. We present an alternative ap...
Abhishek Arun, Barry Haddow, Philipp Koehn, Adam L...
Phrase-based decoding is conceptually simple and straightforward to implement, at the cost of drastically oversimplified reordering models. Syntactically aware models make it pos...